Text Generation
PEFT
Safetensors
Russian
English
gemma4
lora
reasoning
math
agent
tool-use
function-calling
multimodal
russian
unsloth
conversational
4-bit precision
bitsandbytes
Instructions to use rrchat/Cerberus-E4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use rrchat/Cerberus-E4B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B-it") model = PeftModel.from_pretrained(base_model, "rrchat/Cerberus-E4B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Add rrchat integration and mobile web interface guide
Browse files
README.md
CHANGED
|
@@ -126,6 +126,18 @@ Pre-quantized GGUF files (including `Q4_K_M`, `Q5_K_M`, `Q8_0`, `BF16`, and mult
|
|
| 126 |
|
| 127 |
---
|
| 128 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
## Dataset Attribution & Licensing
|
| 130 |
|
| 131 |
Cerberus was trained on a carefully curated, decontaminated multi-source dataset. In accordance with dataset terms and open research best practices, we gratefully acknowledge the following data creators:
|
|
|
|
| 126 |
|
| 127 |
---
|
| 128 |
|
| 129 |
+
## 📱 Recommended Web & Mobile Interface: rrchat
|
| 130 |
+
|
| 131 |
+
Cerberus-E4B pairs seamlessly with **[rrchat](https://github.com/leftik1/rrchat)** — an open-source, mobile-ready AI chat interface:
|
| 132 |
+
|
| 133 |
+
> **Use your local PC's llama.cpp from your phone.** Clean mobile-ready AI chat interface with vision, web search, and privacy.
|
| 134 |
+
|
| 135 |
+
* 🌐 **Project Repository:** [github.com/leftik1/rrchat](https://github.com/leftik1/rrchat)
|
| 136 |
+
* 📷 **Camera & Vision Ready:** Upload photos or snapshots directly from your mobile camera and get instant multimodal visual analysis from Cerberus-E4B.
|
| 137 |
+
* 🔍 **Web Search & Privacy:** Built-in web search capabilities while keeping your inference and chat history 100% private and hosted on your local hardware.
|
| 138 |
+
|
| 139 |
+
---
|
| 140 |
+
|
| 141 |
## Dataset Attribution & Licensing
|
| 142 |
|
| 143 |
Cerberus was trained on a carefully curated, decontaminated multi-source dataset. In accordance with dataset terms and open research best practices, we gratefully acknowledge the following data creators:
|